Privacy-first face recognition that runs on the device
FaceTagr's mobile SDK runs recognition and passive liveness on Android and iOS, including fully offline decisions. Configured attendance workflows can avoid retaining check-in photos or video, while templates and records still require protection. Your chosen enrolment, sync and hosting model determines what is stored or transmitted; customer-built apps and CCTV have their own data flows.
Last reviewed: 18 October 2026 · FaceTagr team
Where does your data go?
| Question | Cloud-dependent matching | FaceTagr offline mobile workflow |
|---|---|---|
| Recognition | Remote server | The device |
| Capture storage | Depends on provider and application | Check-in photos need not be retained in configured workflows |
| Enrolment and templates | Server or application storage | Protected device storage and any chosen enrolment system |
| Sync | Capture or template sent for matching | Only agreed records and templates if configured |
| Network loss | Matching may be unavailable | Matching and liveness continue locally |
| Cost and hardware | Provider fees and connectivity requirements | Device and licence costs; request project pricing |
How do online and offline modes differ?
Offline mode performs recognition and liveness on the device. A cloud or hybrid design can keep capture processing local and use server-side matching. Specify the precise payloads, storage destinations and retention before choosing a mode. No blanket no-image-storage claim applies to every SDK integration or CCTV deployment.
What privacy responsibilities remain?
Face templates are biometric data, even when capture photos are not retained. Define the lawful basis, notice and consent where required, retention, access controls and a workable non-face alternative before rollout. On-device processing does not by itself establish legal compliance.
What assurance can you review?
FaceTagr is ISO 27001 certified and its recognition engine is benchmarked by NIST FRTE. Hosted deployments use SOC 2 Type II-certified infrastructure. Neither these assurances nor local processing is a GDPR certification or automatic legal approval.
Plan a pilot around your workflow
For privacy or deletion requests, contact support@facetagr.com. Read our privacy policy.
Sources
- ICO: biometric recognition guidance
- Illinois BIPA, section 15
- OAIC: statement on the Bunnings Tribunal decision (4 February 2026)
Product capabilities describe FaceTagr's supported workflows, not third-party endorsement. This page is general information, not legal advice. Check your obligations with your data protection officer or adviser.
Frequently Asked Questions
Are workers' photos stored?
Configured mobile attendance workflows can avoid retaining check-in photos or video. Enrolment references, templates and attendance records still need a documented retention policy. Customer-built SDK apps and CCTV may store images according to their configuration; confirm the data flow before deployment.
Does processing on the device remove privacy obligations?
Face templates are biometric data, even when capture photos are not retained. Define the lawful basis, notice and consent where required, retention, access controls and a workable non-face alternative before rollout. On-device processing does not by itself establish legal compliance.
Can it work without a network?
Yes. FaceTagr's mobile SDK supports fully offline 1:1 verification, 1:N identification and passive liveness on Android and iOS. Reporting and integration need a connection when records are synchronised.
Are templates anonymous?
No. Templates used to identify people remain biometric data. Protect them with appropriate access, retention and processing controls.